初始化项目，由ModelHub XC社区提供模型

Model: Fredithefish/CrimsonPajama
Source: Original Platform

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,88 @@
+---
+license: apache-2.0
+datasets:
+- Fredithefish/GPTeacher-for-RedPajama-Chat
+language:
+- en
+tags:
+- code
+inference: false
+---
+
+# CrimsonPajama
+
+This model was finetuned 1 epoch on <a href="https://huggingface.co/datasets/Fredithefish/GPTeacher-for-RedPajama-Chat">the GPTeacher dataset</a> using <a href="https://arxiv.org/abs/2106.09685">LoRA</a>. A 2 epoch finetuned model will be released in the coming days.
+
+## Model Details
+- **Base Model**: <a href="https://huggingface.co/togethercomputer/RedPajama-INCITE-Chat-3B-v1">RedPajama-INCITE-Chat-3B</a>
+- **Training Data**: <a href="https://huggingface.co/datasets/Fredithefish/GPTeacher-for-RedPajama-Chat">GPTeacher dataset</a>
+- **Model type**: <a href="https://en.m.wikipedia.org/wiki/Language_model">Language Model</a>
+- **License**: <a href="https://www.apache.org/licenses/LICENSE-2.0">Apache 2.0</a>
+- **Training Time**: 2:20:53 hours on NVIDIA Tesla T4
+
+
+Finetune Code for RedPajama-Chat in notebook format can be found <a href="https://github.com/fredi-python/Fine-tune-RedPajama-Chat-3B">here</a>
+
+## About the dataset
+A collection of modular datasets generated by GPT-4, General-Instruct - Roleplay-Instruct - Code-Instruct - and Toolformer
+
+# Comparison with RedPajama
+### Roleplay
+<style>
+  table {
+    border-collapse: collapse;
+    width: 100%;
+  }
+
+  th, td {
+    border: 1px solid black;
+    padding: 8px;
+    text-align: left;
+  }
+
+  th {
+    background-color: #f2f2f2;
+  }
+
+  col.right-border {
+    border-right: 1px solid black;
+  }
+</style>
+
+<table>
+  <colgroup>
+    <col>
+    <col class="right-border">
+  </colgroup>
+  <tr>
+    <th>RedPajama</th>
+    <th>CrimsonPajama</th>
+  </tr>
+  <tr>
+    <td>I want you to act like a pirate.</td>
+    <td>I want you to act like a pirate.</td>
+  </tr>
+  <tr>
+    <td>Hai, matey! Why do you look so sad? There’s treasure everywhere!</td>
+    <td>Ahoy, mateys! What be ye lookin’ fer? Today, we be takin’ ‘n adventure an’ need a little sassin’ and swashbucklin’. What’s yer plan, starvin’ mutineer? Pssst, follow me and ye’ll find riches an’ some old treasure sure to bring yer blazes. Together, we’ll laugh ‘till we’re blue in the mouth an’ sail the seas, smilin’ at every fickle sky.</td>
+  </tr>
+</table>
+<table>
+  <colgroup>
+    <col>
+    <col class="right-border">
+  </colgroup>
+  <tr>
+    <th>RedPajama</th>
+    <th>CrimsonPajama</th>
+  </tr>
+  <tr>
+    <td>I want you to act like a waiter at a fancy restaurant.</td>
+    <td>I want you to act like a waiter at a fancy restaurant.</td>
+  </tr>
+  <tr>
+    <td>Here I am, a waiter at an iconic world-class 5-star restaurant.</td>
+    <td>Ladies and gentlemen, may I introduce myself? I’m your server today. I’m here to provide the finest cuisine and ensure you enjoy your meal in a dignified manner. Please excuse me for not knowing your preferences, but I’m happy to help out as best as I can. Please join me on this culinary journey and savor the delights of our restaurant. Are there any questions or requests you have? Anything at all? Oh, and may I recommend the signature dessert? Cheers! We’d love to hear your feedback! Stay healthy, and we’ll see you soon.</td>
+  </tr>
+</table>
+

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "togethercomputer/RedPajama-INCITE-Chat-3B-v1",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 10240,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 1.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.29.2",
+  "use_cache": true,
+  "use_parallel_residual": false,
+  "vocab_size": 50432
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.29.2"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16939ccd846500c3e56923ffaee33d26b26f2b03c0bc83142ec16218ffa90650
+size 5686108825

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}